"""Free path first; hosted path only for videos YouTube blocks.
pip install youtube-transcript-api shephouse-yt
export APIFY_TOKEN=...   # only needed when a block actually happens
"""
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api._errors import RequestBlocked, CouldNotRetrieveTranscript

def get_transcripts(video_ids, languages=("en",), give_up_after=3):
    """Return {video_id: (source, [ {text,start,duration}, ... ]) or Exception}."""
    free = YouTubeTranscriptApi()
    results, blocked, streak = {}, [], 0
    for vid in video_ids:
        if streak >= give_up_after:          # IP is blocked; stop wasting time
            blocked.append(vid)
            continue
        try:
            results[vid] = ("library", free.fetch(vid, languages=languages).to_raw_data())
            streak = 0
        except RequestBlocked:               # includes IpBlocked
            blocked.append(vid)
            streak += 1
        except CouldNotRetrieveTranscript as e:  # no captions, unavailable, ... a real answer
            results[vid] = e
            streak = 0
    if blocked:
        from shephouse_yt import YouTubeTranscriptApi as Hosted
        for vid, r in Hosted().fetch_many(blocked, languages=languages).items():  # one batch run
            results[vid] = r if isinstance(r, Exception) else ("hosted", r.to_raw_data())
    return results

if __name__ == "__main__":
    for vid, r in get_transcripts(["jNQXAC9IVRw", "arj7oStGLkU", "kJQP7kiw5Fk", "AAAAAAAAAAA"]).items():
        if isinstance(r, Exception):
            print(vid, "no transcript:", type(r).__name__)
        else:
            source, snippets = r
            print(vid, source, len(snippets), "snippets:", snippets[0]["text"][:40])